Data Specification and Training Review
This presentation discusses the progress review of training and test data specification for a meeting in January 2021. The content covers topics related to ML4H auditing, advanced robustness testing, and collaboration opportunities. Contact details for further engagement are provided.
Download Presentation
Please find below an Image/Link to download the presentation.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author. If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.
You are allowed to download the files provided on this website for personal or commercial use, subject to the condition that they are used lawfully. All files are the property of their respective owners.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author.
E N D
Presentation Transcript
FGAI4H-K-050 E-meeting, 27-29 January 2021 Source: Editors Title: DEL5.4: Training and test data specification - Progress Review Purpose: Discussion Contact: Luis Oala WG-DAISAM & Fraunhofer HHI Germany Email: luis.oala@hhi.fraunhofer.de Pradeep Balachandran eHealth Consultant Email: pbn.tvm@gmail.com Abstract: This PPT summarizes the content of DEL5.4 for presentation and discussion during the meeting.
DEL 5.4 Training and test data specification Somewhere in cyberspace, January 27, 2021 WG-DAISAM
Context DEL 5.4 FGAI4H-J-48 OCI Training and test data specification
DASP dominik.a.schneider@merckgroup.com shobhaiyer@thebigdataanalytics.com Joachim.krois@charite.de Dominik Shobha Joachim
Research Oala, Luis, Jana Fehr, Luca Gilli, Pradeep Balachandran, Alixandro Werneck Leite, Saul Calderon-Ramirez, Danny Xie Li et al. "ML4H Auditing: From Paper to Practice." In Machine Learning for Health, pp. 280-317. PMLR, 2020. We need plausible robustness testing data Perturbed minds collaboration Bruno Sanguinetti @Dotphoton Christian Matek @ LMU Enrico Pomarico @ HEPIA Geneva Gabriel Nobis @ HHI Marco Aversa @ Dotphoton/Uni Glasgow Kurt Willis @ HHI Luis Oala @ HHI ...
Perturbed minds Processed image Context Reality Raw image Std. image NN output Sanity checks Needs Raw, annotated medical imaging data (brightfield microscopy), e.g. histo, blood smear, Output targets Scientific publications, advanced robustness tests for OCI, improved imaging ML algorithms
Perturbed minds Interested to join? In particular we are interested to access raw, annotated imaging data luis.oala@hhi.fraunofer.de https://app.slack.com/client/T01EDSWE8U8/
